Hugging Face's logo

tf-tpu
/
roberta-base-epochs-500-no-wd

Fill-Mask
Transformers
TensorFlow
roberta
generated_from_keras_callback
Inference Endpoints
Model card Files Community
2
sayakpaul HF staff commited on
Commit
53ad6d9
·
1 Parent(s): f4938c6

Training in progress epoch 0

Browse files
Files changed (2) hide show
  1. README.md +6 -105
  2. tf_model.h5 +1 -1
README.md CHANGED
@@ -14,11 +14,11 @@ probably proofread and complete it, then remove this comment. -->
14
 
15
  This model is a fine-tuned version of [roberta-base](https://huggingface.co/roberta-base) on an unknown dataset.
16
  It achieves the following results on the evaluation set:
17
- - Train Loss: 0.9594
18
- - Train Accuracy: 0.1156
19
- - Validation Loss: 0.9365
20
- - Validation Accuracy: 0.1172
21
- - Epoch: 99
22
 
23
  ## Model description
24
 
@@ -44,106 +44,7 @@ The following hyperparameters were used during training:
44
 
45
  | Train Loss | Train Accuracy | Validation Loss | Validation Accuracy | Epoch |
46
  |:----------:|:--------------:|:---------------:|:-------------------:|:-----:|
47
- | 8.2988 | 0.0215 | 7.1406 | 0.0267 | 0 |
48
- | 6.3403 | 0.0320 | 5.7656 | 0.0339 | 1 |
49
- | 5.5980 | 0.0381 | 5.3906 | 0.0418 | 2 |
50
- | 5.3564 | 0.0434 | 5.2656 | 0.0435 | 3 |
51
- | 5.2256 | 0.0444 | 5.1953 | 0.0433 | 4 |
52
- | 5.1362 | 0.0446 | 5.1016 | 0.0443 | 5 |
53
- | 5.0638 | 0.0446 | 5.0273 | 0.0448 | 6 |
54
- | 5.0062 | 0.0447 | 4.9922 | 0.0444 | 7 |
55
- | 4.9597 | 0.0448 | 4.9492 | 0.0441 | 8 |
56
- | 4.9208 | 0.0448 | 4.8906 | 0.0440 | 9 |
57
- | 4.8839 | 0.0448 | 4.8906 | 0.0444 | 10 |
58
- | 4.8520 | 0.0449 | 4.8398 | 0.0440 | 11 |
59
- | 4.8272 | 0.0449 | 4.8281 | 0.0439 | 12 |
60
- | 4.8004 | 0.0449 | 4.8203 | 0.0440 | 13 |
61
- | 4.7797 | 0.0449 | 4.7734 | 0.0440 | 14 |
62
- | 4.7561 | 0.0449 | 4.7812 | 0.0437 | 15 |
63
- | 4.7384 | 0.0449 | 4.7461 | 0.0443 | 16 |
64
- | 4.7228 | 0.0449 | 4.7109 | 0.0445 | 17 |
65
- | 4.7055 | 0.0449 | 4.6953 | 0.0450 | 18 |
66
- | 4.6916 | 0.0450 | 4.7305 | 0.0444 | 19 |
67
- | 4.6796 | 0.0449 | 4.6914 | 0.0441 | 20 |
68
- | 4.6675 | 0.0450 | 4.7383 | 0.0438 | 21 |
69
- | 4.5396 | 0.0451 | 4.4219 | 0.0457 | 22 |
70
- | 4.2066 | 0.0495 | 3.5312 | 0.0631 | 23 |
71
- | 3.0327 | 0.0723 | 2.4785 | 0.0824 | 24 |
72
- | 2.4182 | 0.0838 | 2.0996 | 0.0910 | 25 |
73
- | 2.1258 | 0.0899 | 1.8877 | 0.0946 | 26 |
74
- | 1.9621 | 0.0933 | 1.8076 | 0.0956 | 27 |
75
- | 1.8554 | 0.0954 | 1.7100 | 0.0986 | 28 |
76
- | 1.7732 | 0.0971 | 1.6123 | 0.1006 | 29 |
77
- | 1.7010 | 0.0986 | 1.5859 | 0.1001 | 30 |
78
- | 1.6423 | 0.0999 | 1.5381 | 0.1019 | 31 |
79
- | 1.5926 | 0.1009 | 1.4863 | 0.1031 | 32 |
80
- | 1.5497 | 0.1019 | 1.4541 | 0.1030 | 33 |
81
- | 1.5123 | 0.1027 | 1.4062 | 0.1051 | 34 |
82
- | 1.4792 | 0.1034 | 1.3896 | 0.1052 | 35 |
83
- | 1.4505 | 0.1040 | 1.3682 | 0.1071 | 36 |
84
- | 1.4229 | 0.1047 | 1.3311 | 0.1072 | 37 |
85
- | 1.3981 | 0.1052 | 1.3008 | 0.1072 | 38 |
86
- | 1.3753 | 0.1057 | 1.2930 | 0.1075 | 39 |
87
- | 1.3548 | 0.1062 | 1.2891 | 0.1077 | 40 |
88
- | 1.3343 | 0.1067 | 1.2686 | 0.1071 | 41 |
89
- | 1.3166 | 0.1071 | 1.2402 | 0.1098 | 42 |
90
- | 1.3008 | 0.1074 | 1.2285 | 0.1097 | 43 |
91
- | 1.2846 | 0.1078 | 1.2100 | 0.1097 | 44 |
92
- | 1.2702 | 0.1081 | 1.1807 | 0.1111 | 45 |
93
- | 1.2568 | 0.1084 | 1.1914 | 0.1109 | 46 |
94
- | 1.2432 | 0.1088 | 1.1943 | 0.1105 | 47 |
95
- | 1.2309 | 0.1090 | 1.1699 | 0.1101 | 48 |
96
- | 1.2196 | 0.1093 | 1.1543 | 0.1117 | 49 |
97
- | 1.2081 | 0.1096 | 1.1699 | 0.1109 | 50 |
98
- | 1.1978 | 0.1098 | 1.1387 | 0.1116 | 51 |
99
- | 1.1878 | 0.1100 | 1.1260 | 0.1118 | 52 |
100
- | 1.1778 | 0.1103 | 1.1025 | 0.1116 | 53 |
101
- | 1.1697 | 0.1105 | 1.1045 | 0.1123 | 54 |
102
- | 1.1617 | 0.1106 | 1.1094 | 0.1124 | 55 |
103
- | 1.1523 | 0.1109 | 1.1025 | 0.1120 | 56 |
104
- | 1.1446 | 0.1110 | 1.1016 | 0.1117 | 57 |
105
- | 1.1362 | 0.1112 | 1.0708 | 0.1126 | 58 |
106
- | 1.1308 | 0.1114 | 1.0840 | 0.1136 | 59 |
107
- | 1.1219 | 0.1116 | 1.0664 | 0.1136 | 60 |
108
- | 1.1158 | 0.1118 | 1.0576 | 0.1133 | 61 |
109
- | 1.1088 | 0.1119 | 1.0449 | 0.1145 | 62 |
110
- | 1.1029 | 0.1121 | 1.0547 | 0.1133 | 63 |
111
- | 1.0953 | 0.1123 | 1.0469 | 0.1136 | 64 |
112
- | 1.0904 | 0.1124 | 1.0337 | 0.1139 | 65 |
113
- | 1.0850 | 0.1125 | 1.0435 | 0.1139 | 66 |
114
- | 1.0787 | 0.1126 | 1.0454 | 0.1144 | 67 |
115
- | 1.0731 | 0.1128 | 1.0312 | 0.1138 | 68 |
116
- | 1.0679 | 0.1130 | 1.0278 | 0.1140 | 69 |
117
- | 1.0634 | 0.1130 | 1.0151 | 0.1152 | 70 |
118
- | 1.0583 | 0.1132 | 1.0215 | 0.1144 | 71 |
119
- | 1.0527 | 0.1133 | 1.0049 | 0.1143 | 72 |
120
- | 1.0482 | 0.1134 | 1.0234 | 0.1134 | 73 |
121
- | 1.0435 | 0.1135 | 1.0249 | 0.1145 | 74 |
122
- | 1.0387 | 0.1137 | 0.9917 | 0.1146 | 75 |
123
- | 1.0355 | 0.1137 | 1.0059 | 0.1150 | 76 |
124
- | 1.0302 | 0.1138 | 0.9834 | 0.1154 | 77 |
125
- | 1.0273 | 0.1139 | 1.0049 | 0.1151 | 78 |
126
- | 1.0229 | 0.1140 | 0.9961 | 0.1150 | 79 |
127
- | 1.0193 | 0.1141 | 0.9863 | 0.1146 | 80 |
128
- | 1.0151 | 0.1142 | 0.9819 | 0.1151 | 81 |
129
- | 1.0116 | 0.1143 | 0.9917 | 0.1148 | 82 |
130
- | 1.0078 | 0.1144 | 0.9893 | 0.1160 | 83 |
131
- | 1.0043 | 0.1145 | 0.9697 | 0.1156 | 84 |
132
- | 1.0017 | 0.1146 | 0.9878 | 0.1150 | 85 |
133
- | 0.9973 | 0.1146 | 0.9683 | 0.1153 | 86 |
134
- | 0.9952 | 0.1147 | 0.9512 | 0.1165 | 87 |
135
- | 0.9907 | 0.1148 | 0.9775 | 0.1154 | 88 |
136
- | 0.9881 | 0.1149 | 0.9541 | 0.1157 | 89 |
137
- | 0.9853 | 0.1149 | 0.9536 | 0.1158 | 90 |
138
- | 0.9813 | 0.1150 | 0.9492 | 0.1154 | 91 |
139
- | 0.9788 | 0.1152 | 0.9585 | 0.1159 | 92 |
140
- | 0.9762 | 0.1152 | 0.9414 | 0.1165 | 93 |
141
- | 0.9738 | 0.1153 | 0.9497 | 0.1148 | 94 |
142
- | 0.9700 | 0.1153 | 0.9375 | 0.1168 | 95 |
143
- | 0.9673 | 0.1154 | 0.9502 | 0.1161 | 96 |
144
- | 0.9656 | 0.1154 | 0.9370 | 0.1190 | 97 |
145
- | 0.9621 | 0.1155 | 0.9473 | 0.1170 | 98 |
146
- | 0.9594 | 0.1156 | 0.9365 | 0.1172 | 99 |
147
 
148
 
149
  ### Framework versions
 
14
 
15
  This model is a fine-tuned version of [roberta-base](https://huggingface.co/roberta-base) on an unknown dataset.
16
  It achieves the following results on the evaluation set:
17
+ - Train Loss: 8.3284
18
+ - Train Accuracy: 0.0211
19
+ - Validation Loss: 7.1523
20
+ - Validation Accuracy: 0.0266
21
+ - Epoch: 0
22
 
23
  ## Model description
24
 
 
44
 
45
  | Train Loss | Train Accuracy | Validation Loss | Validation Accuracy | Epoch |
46
  |:----------:|:--------------:|:---------------:|:-------------------:|:-----:|
47
+ | 8.3284 | 0.0211 | 7.1523 | 0.0266 | 0 |
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
48
 
49
 
50
  ### Framework versions
tf_model.h5 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8430fbde3ad7c57eb35f70632be9d4414c3447279ab9feb7ebc117b606d405ca
3
  size 499741936
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:211105125fcb28cc1eeb845a9624a4f9ded623bf07cbc4221920e36ebe421da6
3
  size 499741936